LangChain Skills is a collection of agent skills for building software agents with LangChain, LangGraph, and Deep Agents. Coding agents that support the Agent Skills specification, including Claude Code, Cursor, and Windsurf, can install and use these skills. The catalogue lists the project's skills and its Claude Code plugin.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add langchain-ai/langchain-skills --skill langgraph-decision-modelsgit clone --depth 1 https://github.com/langchain-ai/langchain-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/langchain-ai/langchain-skills/langgraph-decision-models)<a href="https://agentmods.dev/skills/langchain-ai/langchain-skills/langgraph-decision-models"><img src="https://agentmods.dev/badge/skills/langchain-ai/langchain-skills/langgraph-decision-models/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/langchain-ai/langchain-skills/langgraph-decision-models"><img src="https://agentmods.dev/badge/skills/langchain-ai/langchain-skills/langgraph-decision-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.02261 |
| Opus 5.5 | $0.00032 | $0.00904 |
| Sonnet 5.5 | $0.00016 | $0.00452 |
| Haiku 4.5 | $0.00008 | $0.00226 |
Grade A, and why
langgraph-decision-models scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Noul(instructions=...)— binary question, returns a probability of yesChoice(instructions=..., criteria={...})— picks one label, returns the full distribution plus confidenceScore(instructions=..., criteria=[...])— grades against an ordered rubric, returns an expected value plus confidence
TypeSafeClassifier is a LangChain Runnable[ClassifierRequest, ClassifierResponse], so it drops into a node like any other runnable. Up to 32 questions share one request and are answered independently — your code combines them.
Reach for one when a node generates text only so you can parse a decision out of it: routing, triage, filtering, guardrails, or per-item classification over a batch.
Do not reach for one when the node's output is the product (summaries, drafts, code) or when the judgment needs multi-step reasoning. A decision model classifies; it does not think.
Install and wire
langchain-typesafe is alpha (0.0.1a3) and TypeSafeClassifier is marked @beta — pin it and expect churn.
uv add langchain-typesafe
Three ways to reach a model. The classifier POSTs to {base_url}/v1/systemone with Authorization: Bearer {api_key}, so switching providers is constructor arguments only:
1. TypeSafe directly (Jev). Reads TYPESAFE_API_KEY when api_key is omitted.
classifier = TypeSafeClassifier(model="jev-latest")
2. SemIf, hosted on the LangSmith Gateway. Note: LangSmith key, not a TypeSafe key.
classifier = TypeSafeClassifier( model="semif-qwen3.5-4b", api_key=os.environ["LANGSMITH_API_KEY"], base_url="https://gateway.smith.langchain.com", )
3. Jev through the Gateway (BYOK). The typesafe/ prefix routes to a
TYPESAFE_API_KEY stored in LangSmith workspace secrets. Without that secret
every typesafe/* id returns 424 Failed Dependency -- before the model name is
even validated, so a 424 does not confirm the id is real.
classifier = TypeSafeClassifier( model="typesafe/jev-1.13.0", api_key=os.environ["LANGSMITH_API_KEY"], base_url="https://gateway.smith.langchain.com", )
</python>
</ex-wiring>
---
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 29d ago First seen · 217 lines · 80 tokens per session scan A aed6f94f1b4e
langgraph-decision-models is a skill published in the GitHub repository langchain-ai/langchain-skills (1,313 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 2,261 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…